Embodied Synaptic Plasticity with Online Reinforcement learning
FZI Research Center for Information Technology（FZI信息技术研究中心）；Graz University of Technology（格拉茨技术大学）；Georg-August Universität（哥廷根乔治-奥古斯特大学）；Technische Universität Dresden（德累斯顿工业大学）
Jacques Kaiser, Michael Hoff, Andreas Konle, J. Camilo Vasquez Tieck, David Kappel, Daniel Reichard, Anand Subramoney, Robert Legenstein, Arne Roennau, Wolfgang… 展开作者
Jacques Kaiser, Michael Hoff, Andreas Konle, J. Camilo Vasquez Tieck, David Kappel, Daniel Reichard, Anand Subramoney, Robert Legenstein, Arne Roennau, Wolfgang Maass, Rudiger Dillmann
备注：
18 pages, 5 figures, published in frontiers in neurorobotics
The endeavor to understand the brain involves multiple collaborating research fields. Classically, synaptic plasticity rules derived by theoretical neuroscientists are evaluated in isolation on pattern classification tasks. This contrasts with the biological brain which purpose is to control a body in closed-loop. This paper contributes to bringing the fields of computational neuroscience and robotics closer together by integrating open-source software components from these two fields. The resulting framework allows to evaluate the validity of biologically-plausibe plasticity models in closed-loop robotics environments. We demonstrate this framework to evaluate Synaptic Plasticity with Online REinforcement learning (SPORE), a reward-learning rule based on synaptic sampling, on two visuomotor tasks: reaching and lane following. We show that SPORE is capable of learning to perform policies within the course of simulated hours for both tasks. Provisional parameter explorations indicate that the learning rate and the temperature driving the stochastic processes that govern synaptic learning dynamics need to be regulated for performance improvements to be retained. We conclude by discussing the recent deep reinforcement learning techniques which would be beneficial to increase the functionality of SPORE on visuomotor tasks.
The brain is a nonlinear and highly Recurrent Neural Network (RNN). This RNN is surprisingly plastic and supports our astonishing ability to learn and execute complex tasks. However, learning is incredibly complicated due to the brain's nonlinear nature and the obscurity of mechanisms for determining the contribution of each synapse to the output error. This issue is known as the Credit Assignment Problem (CAP) and is a fundamental challenge in neuroscience and Artificial Intelligence (AI). Nevertheless, in the current understanding of cognitive neuroscience, it is widely accepted that a feedb…
The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and artificial intelligence to understand and model the structure and mechanisms behind the amazing learning capability of the brain. However, in the current understanding of cognitive neuroscience, it is widely accepted that synaptic plasticity plays an essential role in our amazing learning capability. This mechanism is also known as the Credit Assignmen…
Spiking neural networks (SNN) are considered as a perspective basis for performing all kinds of learning tasks - unsupervised, supervised and reinforcement learning. Learning in SNN is implemented through synaptic plasticity - the rules which determine dynamics of synaptic weights depending usually on activity of the pre- and post-synaptic neurons. Diversity of various learning regimes assumes that different forms of synaptic plasticity may be most efficient for, for example, unsupervised and supervised learning, as it is observed in living neurons demonstrating many kinds of deviations from t…
School of Mathematical Sciences（数学科学学院）；School of Psychology, University of Nottingham（诺丁汉大学心理学院）
When training neural networks for classification tasks with backpropagation, parameters are updated on every trial, even if the sample is classified correctly. In contrast, humans concentrate their learning effort on errors. Inspired by human learning, we introduce lazy learning, which only learns on incorrect samples. Lazy learning can be implemented in a few lines of code and requires no hyperparameter tuning. Lazy learning achieves state-of-the-art performance and is particularly suited when datasets are large. For instance, it reaches 99.2% test accuracy on Extended MNIST using a single-la…
The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. W…
We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding the dynamics of learning in the brain, neuroscience-derived models of learning have yet to demonstrate the same performance capabilities as methods in deep learning such as gradient descent. Inspired by the successes of machine learning using gradient descent, we demonstrate that models of neuromodulated synaptic plasticity from neuroscience can be trained in …
Eindhoven University of Technology（埃因霍温理工大学）；University of Trento（特伦托大学）
A learning process with the plasticity property often requires reinforcement signals to guide the process. However, in some tasks (e.g. maze-navigation), it is very difficult (or impossible) to measure the performance of an agent (i.e. a fitness value) to provide reinforcements since the position of the goal is not known. This requires finding the correct behavior among a vast number of possible behaviors without having the knowledge of the reinforcement signals. In these cases, an exhaustive search may be needed. However, this might not be feasible especially when optimizing artificial neural…
As a means of dynamically reconfiguring the synaptic weight of a superconducting optoelectronic loop neuron, a superconducting flux storage loop is inductively coupled to the synaptic current bias of the neuron. A standard flux memory cell is used to achieve a binary synapse, and loops capable of storing many flux quanta are used to enact multi-stable synapses. Circuits are designed to implement supervised learning wherein current pulses add or remove flux from the loop to strengthen or weaken the synaptic weight. Designs are presented for circuits with hundreds of intermediate synaptic weight…
The plasticity property of biological neural networks allows them to perform learning and optimize their behavior by changing their configuration. Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning rules, i.e. rules that update synapses based on the neuron activations and reinforcement signals. However, the distal reward problem arises when the reinforcement signals are not available immediately after each network output to associate the neuron activations that contributed to receiving the reinforcement signal. In this work, we extend Hebbian…
Understanding how biological neural networks carry out learning using spike-based local plasticity mechanisms can lead to the development of powerful, energy-efficient, and adaptive neuromorphic processing systems. A large number of spike-based learning models have recently been proposed following different approaches. However, it is difficult to assess if and how they could be mapped onto neuromorphic hardware, and to compare their features and ease of implementation. To this end, in this survey, we provide a comprehensive overview of representative brain-inspired synaptic plasticity models a…
We propose a model for synaptic plasticity based on a calcium signaling cascade. The model simplifies the full signaling pathways from a calcium influx to the phosphorylation (potentiation) and dephosphorylation (depression) of glutamate receptors that are gated by fictive C1 and C2 catalysts, respectively. This model is based on tangible chemical reactions, including fictive catalysts, for long-term plasticity rather than the conceptual theories commonplace in various models, such as preset thresholds of calcium concentration. Our simplified model successfully reproduced the experimental syna…
Institut Interdisciplinaire d’Innovation Technologique (3IT), Université de Sherbrooke（舍布鲁克大学跨学科技术创新研究所（3IT））；Laboratoire Nanotechnologies Nanosystèmes (LN2) – CNRS UMI-3463, Université de Sherbrooke（舍布鲁克大学纳米技术与纳米系统实验室（LN2）——法国国家科学研究中心联合国际研究单位3463）；Institute of Electronics, Microelectronics and Nanotechnology (IEMN), Université de Lille（里尔大学电子、微电子与纳米技术研究所（IEMN））；Aix Marseille Univ（艾克斯-马赛大学）；Université de Toulon（土伦大学）；CNRS（法国国家科学研究中心）；IM2NP（材料、微电子与纳米科学普罗旺斯研究所（IM2NP））；National Research Council Canada（加拿大国家研究委员会）；University of Waterloo Collaboration Centre（滑铁卢大学合作中心）；Université Paris-Saclay（巴黎萨克雷大学）；Centre de Nanosciences et de Nanotechnologies（纳米科学与纳米技术中心）
This study proposes voltage-dependent-synaptic plasticity (VDSP), a novel brain-inspired unsupervised local learning rule for the online implementation of Hebb's plasticity mechanism on neuromorphic hardware. The proposed VDSP learning rule updates the synaptic conductance on the spike of the postsynaptic neuron only, which reduces by a factor of two the number of updates with respect to standard spike-timing-dependent plasticity (STDP). This update is dependent on the membrane potential of the presynaptic neuron, which is readily available as part of neuron implementation and hence does not r…
Humboldt-Universität zu Berlin（柏林洪堡大学）；University of Trento（特伦托大学）；SAP ML Research（SAP机器学习研究院）
Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized wit…
A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, discusses similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using locally synthesized gradients can overc…
Spike-timing-dependent plasticity (STDP) incurs both causal and acausal synaptic weight updates, for negative and positive time differences between pre-synaptic and post-synaptic spike events. For realizing such updates in neuromorphic hardware, current implementations either require forward and reverse lookup access to the synaptic connectivity table, or rely on memory-intensive architectures such as crossbar arrays. We present a novel method for realizing both causal and acausal weight updates using only forward lookup access of the synaptic connectivity table, permitting memory-efficient im…
Controlling the flow and routing of data is a fundamental problem in many distributed networks, including transportation systems, integrated circuits, and the Internet. In the brain, synaptic plasticity rules have been discovered that regulate network activity in response to environmental inputs, which enable circuits to be stable yet flexible. Here, we develop a new neuro-inspired model for network flow control that only depends on modifying edge weights in an activity-dependent manner. We show how two fundamental plasticity rules (long-term potentiation and long-term depression) can be cast …
IBM Research – Zurich（IBM苏黎世研究院）；Huawei – Zurich Research Center（华为苏黎世研究中心）
Biological neurons and their in-silico emulations for neuromorphic artificial intelligence (AI) use extraordinarily energy-efficient mechanisms, such as spike-based communication and local synaptic plasticity. It remains unclear whether these neuronal mechanisms only offer efficiency or also underlie the superiority of biological intelligence. Here, we prove rigorously that, indeed, the Bayes-optimal prediction and inference of randomly but continuously transforming environments, a common natural setting, relies on short-term spike-timing-dependent plasticity, a hallmark of biological synapses…
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to represent the values of both the input signal and the backpropagated delta value with a series of pulses that trigger multiple positive or negative updates of the synaptic weight, and to use the min operation instead of the product of the two signals. In computational simulations, we show that the proposed approximation to backpropagation is well converged and may be suitable for memristor implementations of multila…
Magnetic skyrmions are promising candidates for next-generation information carriers, owing to their small size, topological stability, and ultralow depinning current density. A wide variety of skyrmionic device concepts and prototypes have been proposed, highlighting their potential applications. Here, we report on a bioinspired skyrmionic device with synaptic plasticity. The synaptic weight of the proposed device can be strengthened/weakened by positive/negative stimuli, mimicking the potentiation/depression process of a biological synapse. Both short-term plasticity(STP) and long-term poten…
Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. In this work, we use networks of leaky integrate-and-fire neurons that are trained to perform both discriminative and generative tasks in their forward and back…
Instituto de Física Interdisciplinar y Sistemas Complejos (IFISC, UIB-CSIC)（跨学科物理与复杂系统研究所（IFISC，巴利阿里群岛大学-西班牙国家研究委员会））；Instituto Carlos I de Física Teórica y Computacional（卡洛斯一世理论与计算物理研究所）
Reservoir Computing (RC) is an appealing approach in Machine Learning that combines the high computational capabilities of Recurrent Neural Networks with a fast and easy training method. Likewise, successful implementation of neuro-inspired plasticity rules into RC artificial networks has boosted the performance of the original models. In this manuscript, we analyze the role that plasticity rules play on the changes that lead to a better performance of RC. To this end, we implement synaptic and non-synaptic plasticity rules in a paradigmatic example of RC model: the Echo State Network. Testing…
A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we present a novel unsupervised learning mechanism ASP (Adaptive Synaptic Plasticity) for improved recognition with Spiking Neural Networks (SNNs) for real time on-line learning in a dynamic environment. We incorporate an adaptive weight decay mechanism with the traditional Spike Timing Dependent Plasticity (STDP) learning to model adaptivity in SNNs. The leak rate o…
Spike-Timing Dependent Plasticity (STDP) is believed to play an important role in learning and the formation of computational function in the brain. The classical model of STDP which considers the timing between pairs of pre-synaptic and post-synaptic spikes (p-STDP) is incapable of reproducing synaptic weight changes similar to those seen in biological experiments which investigate the effect of either higher order spike trains (e.g. triplet and quadruplet of spikes), or, simultaneous effect of the rate and timing of spike pairs on synaptic plasticity. In this paper, we firstly investigate sy…
HRL Laboratories, LLC.（HRL实验室有限责任公司）；University of California Irvine（加州大学欧文分校）
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several efforts towards overcoming catastrophic forgetting in neural networks. Here, we propose a biologically inspired method toward overcoming catastrophic forgetting. Specifically, we define an attention-based selective plasticity of synapses based on the cholinergic neuromodulatory syst…
Qatar University（卡塔尔大学）；Izmir University of Economics（伊兹密尔经济大学）；Aarhus University（奥胡斯大学）；Tampere University（坦佩雷大学）
The recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) that are homogenous only with a linear neuron model. As a heterogenous network model, ONNs are based on a generalized neuron model that can encapsulate any set of non-linear operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data. However, the default search method to find optimal operators in ONNs, the so-called Greedy Iterative Search (GIS) method, usually takes seve…
Triplet-based Spike Timing Dependent Plasticity (TSTDP) is a powerful synaptic plasticity rule that acts beyond conventional pair-based STDP (PSTDP). Here, the TSTDP is capable of reproducing the outcomes from a variety of biological experiments, while the PSTDP rule fails to reproduce them. Additionally, it has been shown that the behaviour inherent to the spike rate-based Bienenstock-Cooper-Munro (BCM) synaptic plasticity rule can also emerge from the TSTDP rule. This paper proposes an analog implementation of the TSTDP rule. The proposed VLSI circuit has been designed using the AMS 0.35 um …
Unsupervised local learning based on voltage-dependent synaptic plasticity for resistive and ferroelectric synapses
Institut Interdisciplinaire d′Innovation Technologique (3IT)（跨学科技术创新研究所）；Université de Sherbrooke（谢布罗克大学）；Laboratoire Nanotechnologies Nanosystèmes (LN2)-IRL3463（纳米技术与纳米系统实验室）；CNRS（法国国家科学研究中心）；INSA Lyon（里昂国立应用科学学院）；Ecole Centrale de Lyon（里昂中央理工大学）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；STMicroelectronics（STMicroelectronics公司）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CEA（法国原子能委员会）；Grenoble INP（格勒诺布尔国立应用科学学院）；SPINTEC（SPINTEC研究中心）；IBM Research GmbH - Zurich Research Laboratory（IBM瑞士研究实验室）；IBM Research GmbH - Zurich Res（IBM瑞士研究实验室）
Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
General results from statistical learning theory suggest to understand not only brain computations, but also brain plasticity as probabilistic inference. But a model for that has been missing. We propose that inherently stochastic features of synaptic plasticity and spine motility enable cortical networks of neurons to carry out probabilistic inference by sampling from a posterior distribution of network configurations. This model provides a viable alternative to existing models that propose convergence of parameters to maximum likelihood values. It explains how priors on weight distributions …
In many normative theories of synaptic plasticity, weight updates implicitly depend on the chosen parametrization of the weights. This problem relates, for example, to neuronal morphology: synapses which are functionally equivalent in terms of their impact on somatic firing can differ substantially in spine size due to their different positions along the dendritic tree. Classical theories based on Euclidean gradient descent can easily lead to inconsistencies due to such parametrization dependence. The issues are solved in the framework of Riemannian geometry, in which we propose that plasticit…
Synaptic plasticity poses itself as a powerful method of self-regulated unsupervised learning in neural networks. A recent resurgence of interest has developed in utilizing Artificial Neural Networks (ANNs) together with synaptic plasticity for intra-lifetime learning. Plasticity has been shown to improve the learning capabilities of these networks in generalizing to novel environmental circumstances. However, the long-term stability of these trained networks has yet to be examined. This work demonstrates that utilizing plasticity together with ANNs leads to instability beyond the pre-specifie…
Short-Term Synaptic Plasticity Stabilizes Goal-Conditioned Dynamics in a PFC-Inspired Reservoir Model for Multistep Goal-Directed Action Planning
Graduate School of Information Science and Technology, The University of Osaka（大阪大学研究生院信息科学技术学院）；School of Systems Information Science, Future University Hakodate（函馆未来大学系统信息科学学院）
